Our work focuses on tackling the challenging but natural visual recognition task of long-
tailed data distribution (ie, a few classes occupy most of the data, while most classes have …

The networks trained on the long-tailed dataset vary remarkably, despite the same training
settings, which shows the great uncertainty in long-tailed learning. To alleviate the …

In recent years, visual recognition on challenging long-tailed distributions, where classes
often exhibit extremely imbalanced frequencies, has made great progress mostly based on …

Despite the success of the deep neural networks, it remains challenging to effectively build a
system for long-tail visual recognition tasks. To address this problem, we first investigate the …

In the real world, large-scale datasets for visual recognition typically exhibit a long-tailed
distribution, where only a few classes contain adequate samples but the others have (much) …

Real-world data typically follow a long-tailed distribution, where a few majority categories
occupy most of the data while most minority categories contain a limited number of samples …

Deep learning has achieved remarkable progress for visual recognition on large-scale
balanced datasets but still performs poorly on real-world long-tailed data. Previous methods …

It's widely acknowledged that deep learning models with flatter minima in its loss landscape
tend to generalize better. However, such property is under-explored in deep long-tailed …

Long-tailed image recognition presents massive challenges to deep learning systems since
the imbalance between majority (head) classes and minority (tail) classes severely skews …

In this paper, our goal is to design a simple learning paradigm for long-tail visual
recognition, which not only improves the robustness of the feature extractor but also …